Skip to main content
Glama
MantisWare

PeepIt MCP

by MantisWare
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OPENAI_API_KEYNoYour OpenAI API key for using OpenAI vision models
PEEPIT_CLI_PATHNoCustom path to the Swift peepit CLI binary
PEEPIT_LOG_FILENoPath to log file. If the directory isn't writable, PeepIt uses a temp folder~/Library/Logs/peepit-mcp.log
PEEPIT_LOG_LEVELNoLogging level: trace, debug, info, warn, error, or fatalinfo
PEEPIT_CLI_TIMEOUTNoTimeout for Swift CLI operations in milliseconds30000
PEEPIT_AI_PROVIDERSNoComma or semicolon-separated list of AI providers for image analysis (e.g., 'openai/gpt-4o,ollama/llava:latest')
PEEPIT_CONSOLE_LOGGINGNoEnable console logging. Set to 'true' to enablefalse
PEEPIT_OLLAMA_BASE_URLNoBase URL for Ollama API if not running at the default locationhttp://localhost:11434
PEEPIT_DEFAULT_SAVE_PATHNoDefault directory for screenshots when no path is specified

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription
imageA

Captures macOS screen content and optionally analyzes it. Targets can be entire screen, specific app window, or all windows of an app (via app_target). Supports foreground/background capture. Output via file path or inline Base64 data (format: "data"). If a question is provided, image is analyzed by an AI model (auto-selected from PEEPIT_AI_PROVIDERS). Window shadows/frames excluded. PeepIt MCP 1.0.0-beta.1 using openai/gpt-4o, ollama/llava:latest

analyzeA

Analyzes a pre-existing image file from the local filesystem using a configured AI model.

This tool is useful when an image already exists (e.g., previously captured, downloaded, or generated) and you need to understand its content, extract text, or answer specific questions about it.

Capabilities:

  • Image Understanding: Provide any question about the image (e.g., "What objects are in this picture?", "Describe the scene.", "Is there a red car?").

  • Text Extraction (OCR): Ask the AI to extract text from the image (e.g., "What text is visible in this screenshot?").

  • Flexible AI Configuration: Can use server-default AI providers/models or specify a particular one per call via 'provider_config'.

Example: If you have an image '/tmp/chart.png' showing a bar chart, you could ask: { "image_path": "/tmp/chart.png", "question": "Which category has the highest value in this bar chart?" } The AI will analyze the image and attempt to answer your question based on its visual content. PeepIt MCP 1.0.0-beta.1 using openai/gpt-4o, ollama/llava:latest

listA

Lists various system items on macOS, providing situational awareness.

Capabilities:

  • Running Applications: Get a list of all currently running applications (names and bundle IDs).

  • Application Windows: For a specific application (identified by name or bundle ID), list its open windows.

    • Details: Optionally include window IDs, bounds (position and size), and whether a window is off-screen.

    • Multi-window apps: Clearly lists each window of the target app.

  • Server Status: Provides information about the PeepIt MCP server itself (version, configured AI providers).

Use Cases:

  • Agent needs to know if 'Photoshop' is running before attempting to automate it. { "item_type": "running_applications" } // Agent checks if 'Photoshop' is in the list.

  • Agent wants to find a specific 'Notes' window to capture. { "item_type": "application_windows", "app": "Notes", "include_window_details": ["ids", "bounds"] } The agent can then use the window title or ID with the 'image' tool. PeepIt MCP 1.0.0-beta.1 using openai/gpt-4o, ollama/llava:latest

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.4/5.0

Scored across 3 tools

Disambiguation5/5

The three tools have clearly distinct purposes with no overlap: 'analyze' processes existing image files, 'image' captures macOS screens and optionally analyzes them, and 'list' provides system information. Each tool targets a different primary function (file analysis, screen capture, system listing), making them easily distinguishable.

Naming Consistency5/5

All tool names follow a consistent, simple verb-based pattern: 'analyze', 'image', and 'list'. While 'image' is a noun rather than a verb, it functions as a clear action (capture image) and maintains a uniform, concise naming style across the set without mixing conventions.

Tool Count5/5

With only 3 tools, the count is well-scoped for the server's purpose of macOS screen interaction and analysis. Each tool serves a distinct, essential function: listing system items for awareness, capturing screens, and analyzing images, covering the core workflow without unnecessary bloat.

Completeness4/5

The tool set covers the primary workflows for macOS screen automation: listing applications/windows, capturing screens, and analyzing images. A minor gap exists in lacking tools for direct interaction with windows (e.g., focus, resize) or file management, but agents can work around this using the provided tools for basic automation tasks.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources